mistralai
Mistral: Mistral Medium 3.1
mistralai/mistral-medium-3.1
Our take
AI-assisted analysis based on the sources below. Suitability is an editorial assessment; test it on your own workload.
mistralai/mistral-medium-3.1 is listed in the OpenRouter catalog as an update to Mistral Medium 3, described by the catalog as an enterprise-grade model aimed at strong performance at reduced operational cost. Per the catalog, it accepts text, image, and file inputs and returns text, with a 131,072-token context window, a June 2025 knowledge cutoff, tool calling, and structured output support. The catalog's attached third-party measurements show modest results in the evaluated design and coding categories. No independent model card was available in this source pack, so all claims rest on catalog data.[1]
Strengths
- The catalog reports multimodal input support (text, image, and file) with text output, plus a large 131,072-token context window.[1]
- According to the catalog, it supports tool calling, tool choice, structured outputs, and response formatting, suiting integration-oriented workflows.[1]
- The catalog positions it as delivering frontier-level capabilities at significantly reduced operational cost; this is catalog positioning, not independent verification.[1]
Limitations
- All evidence comes from the OpenRouter catalog; an independent model card was not available in this source pack, so capabilities remain unverified and require workload validation.[1]
- The catalog's third-party measurements report modest results, with win rates below parity across the listed design-arena categories and a low reported agentic index.[1]
- No dedicated reasoning mode is listed (the reasoning field is null) and the intelligence index is absent; license terms and hardware requirements are unknown.[1]
Where to use it
- Worth evaluating for multimodal ingestion pipelines that combine text, images, and files, subject to validation on your own workloads.[1]
- A candidate for tool-calling and structured-output integrations such as API orchestration or schema-constrained generation, pending task-level testing.[1]
- May fit cost-conscious enterprise assistants per the catalog's positioning, provided measured quality on target tasks is confirmed.[1]
Sources
- [1] OpenRouter catalog · Mistral: Mistral Medium 3.1Sources checked: Nov 13, 2026
About this model
Description below is the original text supplied by OpenRouter, shown in the source language.
Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances...
Specifications
- Model ID
- mistralai/mistral-medium-3.1
- Creator
- mistralai
- Added to OpenRouter
- 13.08.2025
- Context length
- 131,072
- Modality
- text+image+file->text
- Input modalities
- text, image, file
- Output modalities
- text
- Token pricing
- USD per 1M tokens: in $0.400 / out $2
- Knowledge cutoff
- 30.06.2025
- Expiration date
- —
Tasks and capabilities
A grade appears only where the source supplies a matching measurement for that task, the model is active and the cohort holds at least 10 comparable models. The capability column lists facts the source declares — supported formats, reasoning and tool parameters — which are not measured quality.
| Task | Grade | Source-declared capability |
|---|---|---|
| General quality | No measurement | — |
| Coding | CC — below the B band | — |
| Agents | CC — below the B band | parameters: structured_outputs, tool_choice, tools |
| Writing | No measurement | output: text |
| Reasoning | No measurement | — |
| Document analysis | No measurement | input: file |
| Vision | No measurement | input: image |
| Image generation | No measurement | — |
| Audio | No measurement | — |
| Video | No measurement | — |
| Embeddings | No measurement | — |
Evaluations
| Source | Benchmark | Value | Grade | Data retrieved |
|---|---|---|---|---|
| Artificial Analysis | Coding index | 20.5 | CC — below the B band | 13.11.2026 |
| Artificial Analysis | Agentic index | 1.9 | CC — below the B band | 13.11.2026 |
| Design Arena | models · 3dwin rate 44.6% · rank 103 | 1,064Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · asciiartwin rate 30.8% · rank 73 | 993Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · codecategorieswin rate 45.1% · rank 103 | 1,111Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · datavizwin rate 47.2% · rank 86 | 1,142Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · gamedevwin rate 40.8% · rank 112 | 1,065Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · svgwin rate 38.2% · rank 94 | 984Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · uicomponentwin rate 43.6% · rank 105 | 1,090Elo | CC — below the B band | 13.11.2026 |
| Design Arena | models · websitewin rate 46% · rank 104 | 1,127Elo | CC — below the B band | 13.11.2026 |
How grades work
Each letter grade compares a model only against other models scored by the same source and metric in the current snapshot. S means the top 10%, A the next 20%, B the next 30%, C the rest. Models without a published measurement are shown as not rated — a supported format alone never implies measured quality.
- S — S — top 10% of the cohort
- A — A — next 20% of the cohort
- B — B — next 30% of the cohort
- C — C — below the B band
Providers
Optional live provider statistics from OpenRouter. Missing values are unknown, not zero.
| Provider | Context length | Price in /1M | Price out /1M | Latency p50 (30m, s) | Throughput p50 (30m, tok/s) | Uptime (30m) |
|---|---|---|---|---|---|---|
| Mistral | 131,072 | $0.400 | $2 | — | — | 100% |
| Mistral | 131,072 | $0.440 | $2.2 | — | — | 100% |
Provider data retrieved: 13.11.2026
Related articles
No published articles identify this model yet.